Development of improved EIS circuitry for PEM fuel cell module diagnostics systems and incorporation of on-board EIS in fuel cell dc/dc converters

This proposed Mitacs project will investigate and further develop EIS (Electrochemical Impedance Spectroscopy), or AC-impedance-based measurement hardware used for diagnosing faults in PEM (Proton Exchange Membrane) fuel cell systems (FCS), and incorporating the on-board EIS function in the fuel cell dc/dc converters used to transfer power from the fuel cell to the vehicle traction drive.

Enhancing visualization of manufacturing complexity highlights on CAD file

Currently, the service provided by GRAD4 has an interface for visualization of CAD models. However, there is still room for improvement in speed and comprehensibility for the users: both manufacturers and buyers. The main challenge of implementing the improvements is in relatively high computational cost of such visualizations: while a regular PC handles such task efficiently, web-based tools tend to have difficulties when modelling 3D object with similar performance.

Machine Learning based System Suggested Critiquing for in-car Conversational Recommendation

Car Infotainment and Navigation systems to date have only basic interactivity and functionality, and there is nothing in the car today that will keep drivers aware of their surroundings outside the car when the car is in a fully autonomous driving mode. Therefore, we want to contribute in the development of a new in-car infotainment system that is both interactive, personal, contextual (aware of the car’s location and surrounding services).

Design and simulation of an automated robotic solution for the installation of Mechanical, electrical, and plumbing components in wood-framed walls

In this project, a key research project for the robotization of the timber building construction is proposed. By developing a full-scale solution for the installation of MEP components in mass timber walls and showcasing its benefits compared to current manual situations, in terms of safety, quality, productivity and so forth, we expect to support the introduction of robotic cells in offsite construction facilities.

Investigating a dispersive process of nanocellulose reinforced silk protein bone screws to increase its strength

Bone fracture is usually fixed with metal made plates and rods to secure the bone. After the bone heals the plates and rods are usually required to be taken out. The propose of this research is to find a way to create a biomaterial that is strong enough to hold the bones, and can dissolve after the bone is healed, or to convert to another material that will have no effect on normal body function. The partner organization thus partnered with Prof. Sain at university of Toronto to find ways of disperse and create the desired material.

Real-time food analysis using deep learning for Diabetes Self -Monitoring

Our proposed research is to create an algorithm capable of pre-evaluating diabetes patients’ meals before they consume them with the snap of a picture. We are attempting to accomplish this goal by employing AI, machine learning as well as computer vision for real-time analysis. Our goal is to analyse a users meal to return an accurate carb count and offer portion size adjustments to reduce their blood sugar fluctuations.

Implementation and evaluation of a surface estimation algorithm to modify the control of ADAS features

Road departure is a critical factor in vehicle accidents, which could happen as a result of a driver’s impairment or lack of attention, or the road surface condition due to inclement weather. Therefore, it has been a high priority for the automotive industry to improve advanced systems for stability and path control. GM novel approach aims to use a control method to maintain a vehicle in the intended path during automated braking, while the deceleration and collision prevention is optimized.

Automated Driver Drowsiness Control Technology Using Artificial Intelligence-based Decision Support System

The main purpose of this project is to develop the methodology to detect and predict driver drowsiness at the early stages using physical and physiological variables. A feasibility test is conducted to evaluate the accuracy and performance of the proposed methodology. The existing databases are leveraged to extract the required data. Signal processing, image processing, AI techniques and decision-making methods are utilized to analyze data for monitoring, detecting, predicting and controlling driver drowsiness.

3D-Printing for Remote Industries (3DPRI) in Harsh Environments: On the post-processing of a wire arc additive manufactured 420 martensitic stainless steel for enhanced functionality and service life

Newly developed additive manufacturing (AM) techniques, also known as 3D-printing, are able to fabricate complex geometry components at a relatively high deposition rate, the lowest possible number of production cycles, and minimum materials waste in contrast with the conventional subtractive fabrication techniques. By drastic reduction in the fabrication time and production steps, minimizing the on-hold inventory, additive manufacturing technologies have the potential to revolutionize the industrial manufacturing sectors.

Application of machine learning techniques to control surface quality of as-printed wire arc additive manufactured components

Nowadays, the wire arc additive manufacturing is making its path toward providing benefits to aerospace, defense, and oil and gas sectors, ascribed to the process capacity to fabricate components with minimum waste of material and lead time. However, the main challenges associated with the WAAM that have hindered the wide-spread application of the technology include the irregular and random quality of the WAAM fabricated surfaces.